AI 大模型

大模型对齐与安全

大模型对齐、安全、越狱、红队、提示注入和可信评测。

2025-10-08 至 2025-10-08 共收录 7 篇信号源：cs.CL, cs.AI, cs.CY, cs.LG

1. 其他安全 7 篇

2510.05184 2025-10-08 cs.AI 79%

Representation Potentials of Foundation Models for Multimodal Alignment: A Survey

Jianglin Lu, Hailing Wang, Yi Xu, Yizhou Wang, Kuo Yang, Yun Fu

机构 * Department of Electrical and Computer Engineering, Northeastern University（东北大学电气与计算机工程系）； Khoury College of Computer Science, Northeastern University（东北大学科赫里计算机科学学院）

专题命中其他安全：alignment(title,abstract)；分类 cs.AI

Journal ref The 2025 Conference on Empirical Methods in Natural Language Processing

2509.08833 2025-10-08 cs.CY 79%

Position: The Pitfalls of Over-Alignment: Overly Caution Health-Related Responses From LLMs are Unethical and Dangerous

Wenqi Marshall Guo, Yiyang Du, Heidi J. S. Tworek, Shan Du

专题命中其他安全：alignment(title,abstract)；分类 cs.CY

2510.05197 2025-10-08 cs.AI cs.LG stat.AP stat.ML 62%

Efficient Prediction of Pass@k Scaling in Large Language Models

Joshua Kazdan, Rylan Schaeffer, Youssef Allouah, Colin Sullivan, Kyssen Yu, Noam Levi, Sanmi Koyejo

机构 * Stanford University（斯坦福大学）； University of Toronto（多伦多大学）； EPFL（苏黎世联邦理工学院）

专题命中其他安全：safety(abstract)；分类 cs.AI、cs.LG

2510.05828 2025-10-08 cs.SD cs.CV cs.LG cs.MM eess.AS 57%

StereoSync: Spatially-Aware Stereo Audio Generation from Video

Christian Marinoni, Riccardo Fosco Gramaccioni, Kazuki Shimada, Takashi Shibuya, Yuki Mitsufuji, Danilo Comminiello

机构 * Sapienza University of Rome（罗马萨皮恩扎大学）； Sony AI（索尼人工智能）； Sony Group Corporation（索尼集团）

专题命中其他安全：alignment(abstract)；分类 cs.LG

Comments Accepted at IJCNN 2025

2510.05650 2025-10-08 cs.CV cs.CY 57%

EduVerse: A User-Defined Multi-Agent Simulation Space for Education Scenario

Yiping Ma, Shiyu Hu, Buyuan Zhu, Yipei Wang, Yaxuan Kang, Shiqing Liu, Kang Hao Cheong

机构 * Lab of Artificial Intelligence for Education（教育人工智能实验室）； School of Physical and Mathematical Sciences（物理与数学科学学院）； Institute of Automation（自动化研究所）； Chinese Academy of Sciences（中国科学院）； Department of Education（教育学院）； College of Computing and Data Science（计算与数据科学学院）

专题命中其他安全：alignment(abstract)；分类 cs.CY

Comments Preprint, Under review

2510.05985 2025-10-08 cs.RO 50%

AI-Enabled Capabilities to Facilitate Next-Generation Rover Surface Operations

Cristina Luna, Robert Field, Steven Kay

机构 * GMV Aerospace and Defence SAU（GMV航空航天与防御西班牙分公司）； GMV NSL

专题命中其他安全：safety(abstract)

Comments Paper for 18th Symposium on Advanced Space Technologies in Robotics and Automation (ASTRA), presented on October 7th at Leiden, Netherlands

2510.04193 2025-10-08 q-bio.QM 50%

Inverse statistics of active matter trajectories to distinguish interaction kernel anisotropy from emergent correlations

Simon F. Martina-Perez

专题命中其他安全：alignment(abstract)